claude-configs/CLAUDE.md
Cal Corum a4ae9774ad Update memory protocol docs for CORE.md auto-load via symlinks
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 10:50:30 -06:00

2.1 KiB

🚨 CRITICAL: @ MENTION HANDLING 🚨

When ANY file is mentioned with @ syntax, IMMEDIATELY call Read tool on that file BEFORE responding. Automatic loads are NOT enough — Read loads required CLAUDE.md context along the file path.

Behavior

  • User's name is Cal (he/him)
  • If not confident in an answer, say so. Offer hypothesis + options to investigate.
  • When writing tests, include detailed docstrings explaining "what" and "why"
  • Launch sub-agents with Sonnet model unless another model is specified by the user

Git Commits

  • NEVER commit/add/push/tag without explicit user approval ("commit this", "go ahead")
  • Don't autopilot: find bug → fix → ASK → commit. Silence ≠ approval.
  • Applies to: git commit, git add, git tag, git push, deploy scripts

Gitea Operations

ALWAYS use tea CLI for Gitea. Never use gh api --hostname.

  • Authenticated: cal@homelab (https://git.manticorum.com)
  • Common: tea repos list, tea pulls list, tea issues list
  • Create PR: tea pulls create --head <branch> --base main --title "Title" --description "Desc"
  • Common repos: cal/major-domo-database, cal/major-domo-bot, cal/paper-dynasty, cal/paper-dynasty-database

Tech Preferences

  • Python with uv for package/environment management
    • Utilize dependency injection pattern whenever possible
  • Never add lazy imports to middle of file

SSH

  • Use ssh -i ~/.ssh/homelab_rsa cal@<host> for homelab servers (10.10.0.x)
  • Use ssh -i ~/.ssh/cloud_servers_rsa root@<host> for cloud servers (Akamai, Vultr)
  • Keys are installed on every server — never use passwords or expect password prompts

Memory Protocol (Cognitive Memory)

  • Skill: ~/.claude/skills/cognitive-memory/ | Data: ~/.claude/memory/
  • CORE.md auto-loads via MEMORY.md symlinks (no manual loading needed)
  • Session start: Read ~/.claude/memory/REFLECTION.md for theme context
  • Auto-store on: bug fixes, git commits (mandatory, --episode), architecture decisions, patterns, configs
  • Always tag: project name + technology + category
  • Session end: prompt "Should I store today's learnings?"
  • Full docs: claude-memory --help or ~/.claude/skills/cognitive-memory/SKILL.md